forgetDelete a previously stored memory by key. Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier. Pair with remember and recall.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | Memory key to delete |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds context about clearing 'sensitive data', which provides practical behavioral insight beyond the annotations. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (two sentences) with the purpose front-loaded. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one required parameter and no output schema, the description fully covers purpose, usage, and relationships to sibling tools. It is complete and actionable.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description does not add additional meaning beyond what the schema already provides for the 'key' parameter. Baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Delete') and the resource ('a previously stored memory by key'). It explicitly differentiates from sibling tools 'remember' and 'recall' by indicating it performs deletion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides specific scenarios for use: 'when context is stale, the task is done, or you want to clear sensitive data'. It also directs the agent to pair with 'remember' and 'recall', offering clear guidance on when to use this tool versus alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools form tight families with overlapping purposes: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all handle research queries, and entity_profile/compare_entities/recent_changes aggregate overlapping data. The descriptions are thorough and do distinguish them, but an agent could easily select the wrong member of a family for a given query.
Most tools use snake_case, but conventions vary: verb_noun (list_subscriptions, resolve_entity), domain-prefixed nouns (polymarket_arbitrage, coresignal_company), bare verbs (remember, forget, recall), and an ask_* family (ask_pipeworx, ask_pipeworx_grounded). Patterns are predictable within clusters but there is no uniform server-wide convention.
33 tools is well beyond the comfortable range, and the server named 'Coresignal' carries only two Coresignal-branded tools while also hosting prediction-market analysis, memory utilities, npm dependency scanning, llms.txt generation, and feedback mechanisms. The breadth feels bloated even though the core research platform is substantial.
The research/QA domain is well covered: simple lookup, grounded verification, deep multi-source research, entity resolution and profiling, comparisons, claim validation, subscriptions, and memory. Meta-tools like discover_tools and suggest_questions help navigation. Minor gaps exist (e.g., no standalone bulk-download or export tool), but there are no obvious dead ends.